Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    he followed by verbs or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.91
    STRAINT
    0.79
    ій
    0.79
    我看
    0.79
    ள்ளார்
    0.79
    <unused671>
    0.78
    $_{
    0.78
    owymi
    0.77
    idega
    0.77
    ⃣
    0.76
    POSITIVE LOGITS
    и
    1.06
     abol
    0.86
     oblivion
    0.84
     turbulent
    0.83
    ԁ
    0.83
     cusp
    0.82
    ته
    0.81
     westerly
    0.80
    ত্ব
    0.79
     énorm
    0.79
    Act Density 0.000%

    No Known Activations